
Weighted Training for CrossTask Learning
In this paper, we introduce TargetAware Weighted Training (TAWT), a wei...
read it

Characterizing the SLOPE Tradeoff: A Variational Perspective and the DonohoTanner Limit
Sorted l1 regularization has been incorporated into many methods for sol...
read it

Oneshot Differentially Private Topk Selection
Being able to efficiently and accurately select the topk elements witho...
read it

Rejoinder: Gaussian Differential Privacy
In this rejoinder, we aim to address two broad issues that cover most co...
read it

A Central Limit Theorem for Differentially Private Query Answering
Perhaps the single most important use case for differential privacy is t...
read it

LayerPeeled Model: Toward Understanding WellTrained Deep Neural Networks
In this paper, we introduce the LayerPeeled Model, a nonconvex yet anal...
read it

Toward Better Generalization Bounds with Locally Elastic Stability
Classical approaches in learning theory are often seen to yield very loo...
read it

LabelAware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity
As a popular approach to modeling the dynamics of training overparametri...
read it

Sharp Biasvariance Tradeoffs of Hard Parameter Sharing in Highdimensional Linear Regression
Hard parameter sharing for multitask learning is widely used in empiric...
read it

Towards Understanding the Dynamics of the FirstOrder Adversaries
An acknowledged weakness of neural networks is their vulnerability to ad...
read it

A Power Analysis for Knockoffs with the Lasso CoefficientDifference Statistic
In a linear model with possibly many predictors, we consider variable se...
read it

The Complete Lasso Tradeoff Diagram
A fundamental problem in the highdimensional regression is to understan...
read it

The Price of Competition: Effect Size Heterogeneity Matters in High Dimensions
In highdimensional linear regression, would increasing effect sizes alw...
read it

On Learning Rates and Schrödinger Operators
The learning rate is perhaps the single most important parameter in the ...
read it

Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion
Datasets containing sensitive information are often sequentially analyze...
read it

Deep Learning with Gaussian Differential Privacy
Deep learning models are often trained on datasets that contain sensitiv...
read it

The Local Elasticity of Neural Networks
This paper presents a phenomenon in neural networks that we refer to as ...
read it

Gaussian Differential Privacy
Differential privacy has seen remarkable success as a rigorous and pract...
read it

Acceleration via Symplectic Discretization of HighResolution Differential Equations
We study firstorder optimization methods obtained by discretizing ordin...
read it

The FDRLinking Theorem
This paper introduces the FDRlinking theorem, a novel technique for und...
read it

Understanding the Acceleration Phenomenon via HighResolution Differential Equations
Gradientbased optimization algorithms can be studied from the perspecti...
read it

Differentially Private False Discovery Rate Control
Differential privacy provides a rigorous framework for privacypreservin...
read it

Robust Inference Under Heteroskedasticity via the Hadamard Estimator
Drawing statistical inferences from large datasets in a modelrobust way...
read it
Weijie J. Su
is this you? claim profile